fixed cleanup script

This commit is contained in:
N_T 2024-10-09 10:36:24 +08:00
parent 2db1f59d24
commit 1548db1731
3 changed files with 1202 additions and 1267 deletions

File diff suppressed because one or more lines are too long

View File

@ -8,152 +8,154 @@ pdfMode = True
print(format(sys.argv))
if len(sys.argv)>1:
if int(sys.argv[1])>0:
print("WWW mode on")
pdfMode = False
if int(sys.argv[1])>0:
print("WWW mode on")
pdfMode = False
fileList = [
"diffphys-code-burgers.ipynb", "diffphys-code-ns.ipynb", "diffphys-code-sol.ipynb", "physicalloss-code.ipynb", # TF
"bayesian-code.ipynb", "supervised-airfoils.ipynb", # pytorch
"reinflearn-code.ipynb", # phiflow
"physgrad-comparison.ipynb", # jax
"physgrad-code.ipynb", # pip
]
"diffphys-code-burgers.ipynb", "diffphys-code-ns.ipynb", "diffphys-code-sol.ipynb", "physicalloss-code.ipynb", # TF
"bayesian-code.ipynb", "supervised-airfoils.ipynb", # pytorch
"reinflearn-code.ipynb", # phiflow
"physgrad-comparison.ipynb", # jax
"physgrad-code.ipynb", # pip
]
#fileList = [ "physgrad-code.ipynb"] # debug, only 1 file
#fileList = [ "t1.ipynb" ] # debug
#fileList = [ "diffphys-code-sol.ipynb" ] # debug
# main
for fnOut in fileList:
if not os.path.isfile(fnOut):
print("Error: "+fnOut+" not found!"); exit(1)
if not os.path.isfile(fnOut):
print("Error: "+fnOut+" not found!"); exit(1)
# create backups
fn0 = fnOut[:-5] + "bak"
fn = fn0 + "0"; cnt = 0
while os.path.isfile(fn):
#print("Error: "+fn+" already exists!"); exit(1)
print("Warning: "+fn+" already exists!")
fn = fn0 + format(cnt); cnt=cnt+1
# create backups
fn0 = fnOut[:-5] + "bak"
fn = fn0 + "0"; cnt = 0
while os.path.isfile(fn):
#print("Error: "+fn+" already exists!"); exit(1)
print("Warning: "+fn+" already exists!")
fn = fn0 + format(cnt); cnt=cnt+1
print("renaming "+fnOut+ " to "+fn )
if os.path.isfile(fnOut):
os.rename(fnOut, fn)
if not os.path.isfile(fn):
print("Error: "+fn+" missing!")
exit(1)
print("renaming "+fnOut+ " to "+fn )
if os.path.isfile(fnOut):
os.rename(fnOut, fn)
if not os.path.isfile(fn):
print("Error: "+fn+" missing!")
exit(1)
with open(fn) as file:
d = json.load(file)
with open(fn) as file:
d = json.load(file)
#print(d.keys()) #print(d["cells"][0].keys())
#print(d.keys()) #print(d["cells"][0].keys())
# remove TF / pytorch warnings, build list of regular expressions to search for
# double check, redundant with removing stderr cells (cf delE)
res = []
res.append( re.compile(r"WARNING:tensorflow:") )
res.append( re.compile(r"UserWarning:") )
res.append( re.compile(r"DeprecationWarning:") )
res.append( re.compile(r"InsecureRequestWarning") ) # for https download
res.append( re.compile(r"Building wheel") ) # phiflow install, also gives weird unicode characters
res.append( re.compile(r"warnings.warn") ) # phiflow warnings
res.append( re.compile(r"WARNING:absl") ) # jax warnings
# remove TF / pytorch warnings, build list of regular expressions to search for
# double check, redundant with removing stderr cells (cf delE)
res = []
res.append( re.compile(r"WARNING:tensorflow:") )
res.append( re.compile(r"UserWarning:") )
res.append( re.compile(r"DeprecationWarning:") )
res.append( re.compile(r"InsecureRequestWarning") ) # for https download
res.append( re.compile(r"Building wheel") ) # phiflow install, also gives weird unicode characters
res.append( re.compile(r"warnings.warn") ) # phiflow warnings
res.append( re.compile(r"WARNING:absl") ) # jax warnings
res.append( re.compile(r"ERROR: pip") ) # pip dependencies
res.append( re.compile(r"requires imgaug") ) # pip dependencies
res.append( re.compile(r"See the documentation of nn.Upsample") ) # pip dependencies
res.append( re.compile(r"ERROR: pip") ) # pip dependencies
res.append( re.compile(r"requires imgaug") ) # pip dependencies
res.append( re.compile(r"See the documentation of nn.Upsample") ) # pip dependencies
# remove all "warnings.warn" from phiflow?
# remove all "warnings.warn" from phiflow?
# shorten data line: "0.008612174447657694, 0.02584669669548606, 0.043136357266407785"
reD = re.compile(r"\[0.008612174447657694, 0.02584669669548606, 0.043136357266407785.+\]" )
reDt = "[0.008612174447657694, 0.02584669669548606, 0.043136357266407785 ... ]"
# shorten data line: "0.008612174447657694, 0.02584669669548606, 0.043136357266407785"
reD = re.compile(r"\[0.008612174447657694, 0.02584669669548606, 0.043136357266407785.+\]" )
reDt = "[0.008612174447657694, 0.02584669669548606, 0.043136357266407785 ... ]"
t="cells"
okay = 0
deletes = 0
for i in range(len(d[t])):
#for i in range(len(d[t])):
#print(d[t][0]["cell_type"])
#print(d[t][i]["cell_type"])
t="cells"
okay = 0
deletes = 0
for i in range(len(d[t])):
#for i in range(len(d[t])):
#print(d[t][0]["cell_type"])
#print(d[t][i]["cell_type"])
# remove images after code
# remove images after code
if d[t][i]["cell_type"]=="code":
#print(d[t][i].keys())
#d[t][i]["outputs"] = ""
#print(d[t][i]["outputs"])
if d[t][i]["cell_type"]=="code":
#print(d[t][i].keys())
#d[t][i]["outputs"] = ""
#print(d[t][i]["outputs"])
if pdfMode:
for j in range(len( d[t][i]["source"] )):
#print( d[t][i]["source"][j] )
#print( type(d[t][i]["source"][j] ))
dsOut = reD.sub( reDt, d[t][i]["source"][j] ) # replace long number string (only for burgers)
d[t][i]["source"][j] = dsOut
deletes = deletes+1
#print( d[t][i]["source"][j] +"\n >>> \n" +d2 )
if pdfMode:
for j in range(len( d[t][i]["source"] )):
#print( d[t][i]["source"][j] )
#print( type(d[t][i]["source"][j] ))
dsOut = reD.sub( reDt, d[t][i]["source"][j] ) # replace long number string (only for burgers)
d[t][i]["source"][j] = dsOut
deletes = deletes+1
#print( d[t][i]["source"][j] +"\n >>> \n" +d2 )
delE = [] # collect whole entries (sections) to delete
delE = [] # collect whole entries (sections) to delete
#print(len( d[t][i]["outputs"] ))
for j in range(len( d[t][i]["outputs"] )):
#print(type( d[t][i]["outputs"][j] ))
#print( d[t][i]["outputs"][j].keys() )
#print(len( d[t][i]["outputs"] ))
for j in range(len( d[t][i]["outputs"] )):
#print(type( d[t][i]["outputs"][j] ))
#print( d[t][i]["outputs"][j].keys() )
# search for error stderr cells
if d[t][i]["outputs"][j]["output_type"]=="stream":
#print("output j name: "+ format( d[t][i]["outputs"][j]["name"] ) )
#print("output j: "+ format( d[t][i]["outputs"][j] ) )
if d[t][i]["outputs"][j]["name"]=="stderr":
print("stderr found! len text "+ format(len( d[t][i]["outputs"][j]["text"]) ) +", removing entry "+format(j) )
delE.append(j) # remove the whole stderr entry
# search for error stderr cells
if d[t][i]["outputs"][j]["output_type"]=="stream":
#print("output j name: "+ format( d[t][i]["outputs"][j]["name"] ) )
#print("output j: "+ format( d[t][i]["outputs"][j] ) )
if d[t][i]["outputs"][j]["name"]=="stderr":
print("stderr found! len text "+ format(len( d[t][i]["outputs"][j]["text"]) ) +", removing entry "+format(j) )
delE.append(j) # remove the whole stderr entry
# images
if d[t][i]["outputs"][j]["output_type"]=="stream":
#print("len "+ format(len( d[t][i]["outputs"][j]["text"] )) )
# images
if d[t][i]["outputs"][j]["output_type"]=="stream":
#print("len "+ format(len( d[t][i]["outputs"][j]["text"] )) )
dell = [] # collect lines to delete
for k in range( len( d[t][i]["outputs"][j]["text"] ) ):
#print(" tout "+ d[t][i]["outputs"][j]["text"][k] ) # debug , print all lines
nums = []; all_good = True
for rr in range(len(res)):
nums.append( res[rr].search( d[t][i]["outputs"][j]["text"][k] ) )
if nums[-1] is not None:
all_good = False # skip!
dell = [] # collect lines to delete
for k in range( len( d[t][i]["outputs"][j]["text"] ) ):
#print(" tout "+ d[t][i]["outputs"][j]["text"][k] ) # debug , print all lines - ACTIVATE to LOCATE errors
nums = []; all_good = True
for rr in range(len(res)):
nums.append( res[rr].search( d[t][i]["outputs"][j]["text"][k] ) )
if nums[-1] is not None:
all_good = False # skip!
if all_good:
okay = okay+1
else: # delete line "dell"
deletes = deletes+1
dell.append(d[t][i]["outputs"][j]["text"][k])
#print( format(nums) +" " + d[t][i]["outputs"][j]["text"][k] ) # len( d[t][i]["outputs"][j]["text"][k] ) )
if all_good:
okay = okay+1
else: # delete line "dell"
deletes = deletes+1
dell.append(d[t][i]["outputs"][j]["text"][k])
#print( format(nums) +" " + d[t][i]["outputs"][j]["text"][k] ) # len( d[t][i]["outputs"][j]["text"][k] ) )
for dl in dell:
d[t][i]["outputs"][j]["text"].remove(dl)
#print("len after "+format( len( d[t][i]["outputs"][j]["text"] )) + " A") # debug
for dl in dell:
d[t][i]["outputs"][j]["text"].remove(dl)
#print("len after "+format( len( d[t][i]["outputs"][j]["text"] )) + " A") # debug
# afterwards (potentially remove whole entries)
# if len(delE)>0:
# print("len bef "+format( len( d[t][i]["outputs"] )) + " A " + format(delE)) # debug
for de in delE:
#print(type(d[t][i]["outputs"])); print(de)
d[t][i]["outputs"].pop(de) # remove array element
deletes+=1
# if len(delE)>0:
# print("len after "+format( len( d[t][i]["outputs"] )) + " A") # debug
# afterwards (potentially remove whole entries)
if len(delE)>0:
delE.sort(reverse=True)
#print("len bef "+format( len( d[t][i]["outputs"] )) + " A " + format(delE)) # debug
for de in delE:
#print(type(d[t][i]["outputs"])); print(de)
d[t][i]["outputs"].pop(de) # remove array element
deletes+=1
# if len(delE)>0:
# print("len after "+format( len( d[t][i]["outputs"] )) + " A") # debug
if deletes==0:
print("Warning: Nothing found in "+fn+"!")
if not os.path.isfile(fnOut):
os.rename(fn, fnOut)
else:
print("Error, both files exist!?")
exit(1)
if deletes==0:
print("Warning: Nothing found in "+fn+"!")
if not os.path.isfile(fnOut):
os.rename(fn, fnOut)
else:
print("Error, both files exist!?")
exit(1)
else:
print(" ... writing "+fnOut )
with open(fnOut,'w') as fileOut:
json.dump(d,fileOut, indent=1, sort_keys=True)
else:
print(" ... writing "+fnOut )
with open(fnOut,'w') as fileOut:
json.dump(d,fileOut, indent=1, sort_keys=True)

View File

@ -10,7 +10,6 @@ echo
echo WARNING - still requires one manual quit of first pdf/latex pass, use shift-x to quit
echo
PYT=python3.7
PYT=python3
# warning - modifies notebooks!
@ -18,9 +17,21 @@ ${PYT} json-cleanup-for-pdf.py
# clean / remove _build dir ?
# GEN!
/Users/thuerey/Library/Python/3.9/bin/jupyter-book build .
xelatex book
exit # sufficient for newer jupyter book versions
# old "pre" GEN
#/Users/thuerey/Library/Python/3.7/bin/jupyter-book build . --builder pdflatex
/Users/thuerey/Library/Python/3.9/bin/jupyter-book build . --builder pdflatex
#/Users/thuerey/Library/Python/3.9/bin/jupyter-book build . --builder pdflatex
# old cleanup
cd _build/latex
#mv book.pdf book-xetex.pdf # not necessary, failed anyway